Archive
AI 晶片、GPU、資料中心、邊緣裝置與硬體安全。
GitHub Repo
Reports filed on October 7 for PyTorch and TorchTitan indicate that copy-on-write tensors materialized during CUDA Graph capture may omit the copy operation, causing incorrect results on replay. The reports include a minimal reproduction and an MoE inference comparison, but the impact on released versions and an upstream fix remain unconfirmed.
GitHub Repo
A reproduction on the October 7 development build suggests that appending multiple tokens after reusing a prefix may leave more than the configured threshold in the full-precision cache. The report includes a test that requires no weight downloads, but maintainers have not confirmed the issue, and GPU memory and output-quality effects have not been verified.
最新模型
On October 7, Liquid AI released d1-3B and the experimental d1-omni-600M, which return structured decisions without generating answers token by token. Local and Jetson deployment examples are available, but the low-latency figures depend on warm-up conditions, and evaluation results are still primarily based on the company’s own testing.
GitHub Repo
A community report dated October 7 says that after an Ollama update wrote model manifests as symbolic links, Windows refused to read them, causing CLI and API requests to fail. The report includes file attributes and migration logs, but whether Developer Mode is a trigger remains unconfirmed upstream.
GitHub Repo
A community report dated October 6 says image requests to Qwen3-VL may repeatedly crash the inference process when another large model is already using both GPUs. The report includes a core-dump stack trace, but maintainers have yet to confirm whether memory pressure caused a null-pointer error.
GitHub Repo
A PyTorch community reproduction on October 5 found that Inductor may drop an addition’s alpha coefficient under a specific combination of clipping and scaling. A draft fix was proposed on October 6 but has not been merged; the impact on full training runs remains to be verified.
GitHub Repo
A community report on October 5 says Ollama may reuse output indexes and omit a message completion event when it emits text before a tool call. The proposed fix includes regression tests but has not been merged or validated with actual model inference.
GitHub Repo
A community report involving Transformers 5.12.0 says that after enabling the CPU memory-efficient loading option, other training processes may still allocate a full model, exhausting host memory. Official documentation says the option should prevent duplicate loading across processes, but the root cause and fix status await upstream confirmation.
GitHub Repo
A reproduction on a PyTorch development build shows that CUDA bicubic interpolation may return the input unchanged when a non-integer scale factor still produces the same output dimensions. A fix has been proposed but not merged; the impact on released versions remains unconfirmed.
GitHub Repo
A reproduction on the vLLM development branch shows that, even with batch invariance enabled, model metadata caching and module import order may still change inference results. The community has proposed a fix, but it has not yet been merged; the impact on released versions and other hardware remains to be confirmed.
GitHub Repo
A community reproduction on Ollama 0.35.1 suggests that `lfm2:24b` may omit certain Python strings, altering JSON values and document content. Upstream has yet to confirm the issue, and there is not enough evidence to determine whether it stems from tokenizer decoding, model packaging, or the hardware path.
GitHub Repo
A community report involving vLLM 0.30.0 suggests that adding `chat_template_kwargs` to image requests may leave the model with text only, while the server still returns success. The issue has yet to be confirmed upstream; deployments combining visual input with thinking-mode controls should verify the actual input.